Dynamic positron emission tomography (dPET) image reconstruction is extremely challenging due to the limited counts received in individual frame. In this paper, we propose a spatial-temporal convolutional primal dual ...
详细信息
ISBN:
(纸本)9781665473583
Dynamic positron emission tomography (dPET) image reconstruction is extremely challenging due to the limited counts received in individual frame. In this paper, we propose a spatial-temporal convolutional primal dual network (STPDnet) for dynamic PET image reconstruction. Both spatial and temporal correlations are encoded by 3D convolution operators. The physical projection of PET is embedded in the iterative learning process of the network, which provides the physical constraints and enhances interpretability. The experiments of real rat scan data have shown that the proposed method can achieve substantial noise reduction in both temporal and spatial domains and outperform the maximum likelihood expectation maximization (MLEM), spatial-temporal kernel method (KEM-ST), deepPET and Learned Primal Dual (LPD).
Regularization by denoising (RED) is a widely-used framework for solving inverse problems by leveraging image denoisers as image priors. Recent work has reported the stateof-the-art performance of RED in a number of i...
详细信息
ISBN:
(数字)9781665496209
ISBN:
(纸本)9781665496209
Regularization by denoising (RED) is a widely-used framework for solving inverse problems by leveraging image denoisers as image priors. Recent work has reported the stateof-the-art performance of RED in a number of imaging applications using pre-trained deep neural nets as denoisers. Despite the recent progress, the stable convergence of RED algorithms remains an open problem. The existing RED theory only guarantees stability for convex data-fidelity terms and nonexpansive denoisers. This work addresses this issue by developing a new monotone RED (MRED) algorithm, whose convergence does not require nonexpansiveness of the deep denoising prior. Simulations on image deblurring and compressive sensing recovery from random matrices show the stability of MRED even when the traditional RED diverges.
Ultrafast pulse-echo ultrasound imaging is performed by recording only one measurement cycle, which insonifies the entire region of interest. It has been shown that mathematical model of the received signal is suitabl...
详细信息
ISBN:
(纸本)9789464593617;9798331519773
Ultrafast pulse-echo ultrasound imaging is performed by recording only one measurement cycle, which insonifies the entire region of interest. It has been shown that mathematical model of the received signal is suitable for image reconstruction based on sparsity-promoting algorithms if material parameters of measurement area can be sparsely represented with a suitable basis. However, reconstruction performance of these algorithms is affected by correlation of measured samples, which depends on the scatterer locations in the measurement area and transmitted signal parameters. In this paper, we create a model-based and self-supervised neural network, which learns the transmitted waveforms and delays of each transducer element with the task of minimizing the reconstruction error. It employs forward model as encoder and the Fast Iterative Shrinkage Thresholding Algorithm as decoder. The outcomes are evaluated against two existing scenarios: one involving randomly delayed and weighted transmission signals, and the other based on conventional plane wave imaging. Utilizing learned transmission waveform and time delays outperformed other cases in terms of contrast level and reconstruction accuracy.
Sparse representation (SR) is a widely accepted hyperspectral image (HSI) denoising model. Because of the curse of dimensionality and the desire to better fit the data, the SR models are typically deployed on small an...
详细信息
ISBN:
(数字)9781665427920
ISBN:
(纸本)9781665427920
Sparse representation (SR) is a widely accepted hyperspectral image (HSI) denoising model. Because of the curse of dimensionality and the desire to better fit the data, the SR models are typically deployed on small and fully overlapping blocks whose results are averaged to produce the global denoised HSI. This "local-global" denoising mechanism ignores the dependencies between blocks, resulting in visual artifacts. This paper describes the underlying clean HSI with a 3D convolutional sparse coding (CSC) model, representing the HSI with a linear combination of few shift-invariant 3D spatial-spectral filters in a global dictionary. Instead of operating on patches, the CSC model sees the clean HSI is generated from a sum of local atoms that appear in a small number of locations throughout the image, naturally retaining the relationship between pixels. Moreover, we unfold the optimization process of the model into a spatial-spectral convolutional sparse neural network which absorbs the interpretation ability of the model while supporting discriminative learning from data. Experimental results on both synthetic and real-world datasets show that our network achieves competitive denoising performances, qualitatively and quantitatively.
Recently, many forms of audio industrial applications, such as sound monitoring and source localization, have begun exploiting smart multi-modal devices equipped with a microphone array. Regrettably, model-based metho...
详细信息
Recently, many forms of audio industrial applications, such as sound monitoring and source localization, have begun exploiting smart multi-modal devices equipped with a microphone array. Regrettably, model-based methods are often difficult to employ for such devices due to their high computational complexity, as well as the difficulty of appropriately selecting the user-determined parameters. As an alternative, one may use deep network-based methods, but these are often difficult to generalize, nor can they generate the desired beamforming map directly. In this paper, a computationally efficient acoustic beamforming algorithm is proposed, which may be unrolled to form a model-based deep learning network for real-time imaging, here termed the DAMAS-FISTA-Net. By exploiting the natural structure of an acoustic beamformer, the proposed network inherits the physical knowledge of the acoustic system, and thus learns the underlying physical properties of the propagation. As a result, all the network parameters may be learned end-to-end, guided by a model-based prior using back-propagation. Notably, the proposed network enables an excellent interpretability and the ability of being able to process the raw data directly. Extensive numerical experiments using both simulated and real-world data illustrate the preferable performance of the DAMAS-FISTA-Net as compared to alternative approaches.
Objective. Dynamic positron emission tomography (PET) imaging, which can provide information on dynamic changes in physiological metabolism, is now widely used in clinical diagnosis and cancer treatment. However, the ...
详细信息
Objective. Dynamic positron emission tomography (PET) imaging, which can provide information on dynamic changes in physiological metabolism, is now widely used in clinical diagnosis and cancer treatment. However, the reconstruction from dynamic data is extremely challenging due to the limited counts received in individual frame, especially in ultra short frames. Recently, the unrolled model-based deep learning methods have shown inspiring results for low-count PET image reconstruction with good interpretability. Nevertheless, the existing model-based deep learning methods mainly focus on the spatial correlations while ignore the temporal domain. Approach. In this paper, inspired by the learned primal dual (LPD) algorithm, we propose the spatio-temporal primal dual network (STPDnet) for dynamic low-count PET image reconstruction. Both spatial and temporal correlations are encoded by 3D convolution operators. The physical projection of PET is embedded in the iterative learning process of the network, which provides the physical constraints and enhances interpretability. Main results. The experiments of both simulation data and real rat scan data have shown that the proposed method can achieve substantial noise reduction in both temporal and spatial domains and outperform the maximum likelihood expectation maximization, spatio-temporal kernel method, LPD and FBPnet. Significance. Experimental results show STPDnet better reconstruction performance in the low count situation, which makes the proposed method particularly suitable in whole-body dynamic imaging and parametric PET imaging that require extreme short frames and usually suffer from high level of noise.
暂无评论